MaxPoolBackward¶

General¶

AvgPoolBackward operation accepts \(\src\) tensor and \(\diffdst\) tensor, and calculates \(\diffsrc\) tensor.

Attribute Name	De
strides	Controls the strides the window is moved.	s64	A s64 list containing positive values	Required
pads_begin	Controls number of zeros to be add to the front/top/left of spatial dimensions, the attribute will be ignored when `auto_pad` attribute is specified to `same_upper` , `same_lower` or `valid` .	s64	A s64 list containing non-negative values	Required
pads_end	Controls number of zeros to be add to the back/bottom/right of spatial dimensions, the attribute will be ignored when `auto_pad` attribute is specified to `same_upper` , `same_lower` or `valid` .	s64	A s64 list containing non-negative values	Required
kernel	Size of pooling window	s64	A s64 list containing positive values	Required
auto_pad	Controls how the paddings are calculated.	string	`none` (default), `same_upper` , `same_lower` , `valid`	Optional
dilations	Denotes the distance in width and height between elements in the window.	s64	A s64 list containing positive values, a list of `1` s (default) means no dilation	Optional
data_format	Controls how to interpret the shape of `src` and `dst` .	string	`NCX` , `NXC` (default)	Optional

The inputs and outputs must be provided according to below index order when constructing an operation.

Index	Argu
0	`src`	Required
1	`diff_dst`	Required

Index	Argu
0	`diff_src`	Required

MaxPoolBackward operation supports the following data type combinations.

MaxPool Minimum